Name: pendo
Rating: 67.2 (1 reviews)
Author: membranedev

pendo

Pendo integration. Manage Guides, Segments, Pages, Features, Feedbacks, Polls. Use when the user wants to interact with Pendo data.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is command-driven, well-structured, and actionable with a clear connection-state workflow. It scores just below the top tier due to some rationale over-explanation, placeholder-laden examples, and the absence of validation feedback loops for destructive operations.

Suggestions

Add a verify/retry checkpoint after destructive or mutating calls (e.g., re-fetch a Guide after running an action on it, or check the response status before proceeding) to push workflow clarity to 5.

Tighten rationale sentences (the Membrane auth explanation and "burn less tokens" commentary) so only commands and choices Claude cannot infer remain.

Resolve placeholder duplication: the action-list command appears twice with slightly different forms ("Popular actions" vs "Searching for actions"); consolidate into one canonical example.

Dimension	Reasoning	Score
Conciseness	Mostly efficient command-first guidance with little generic padding, though sentences like "This skill uses the Membrane CLI to interact with Pendo. Membrane handles authentication and credentials refresh automatically — so you can focus on the integration logic rather than auth plumbing." over-explain rationale Claude could infer.	4 / 5
Actionability	Provides concrete, runnable commands (install, login, connection ensure/get, action list/run, request) with flags; minor gaps such as placeholders like QUERY and CONNECTION_ID and the doubled action-list examples keep it just below fully copy-paste-ready.	4 / 5
Workflow Clarity	The connection setup flow is clearly sequenced with explicit state-based decision branches (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) and polling checkpoints; it is not a 5 because there is no validate-then-retry feedback loop and the destructive proxy/action paths lack verification steps.	4 / 5
Progressive Disclosure	Well-organized single-file overview with clear section headers and no nested references; since no bundle files exist and the skill is short, structure is good but a few sections (e.g., the proxy flag table, repeated action-list guidance) could live in reference files to reach the clean one-level split of 5.	4 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly answers both what it does and when to use it with Pendo-specific trigger entities, giving it strong completeness and distinctiveness. It is held just below full marks on specificity and trigger-term quality by the repetitive "Manage" verb and the absence of synonyms.

Suggestions

Vary the verb beyond a single "Manage" (e.g., "Create and manage Guides, query Segments, list Pages") to show distinct concrete actions and lift specificity.

Add natural synonyms or phrasings a user might say (e.g., "Pendo guides", "in-app guides", "user segments") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Manage Guides, Segments, Pages, Features, Feedbacks, Polls") but the verbs are uniform ("Manage") rather than multiple distinct actions, leaving minor gaps versus the comprehensive-coverage anchor at 5.	4 / 5
Completeness	Explicitly states what it does ("Manage Guides, Segments, Pages, Features, Feedbacks, Polls") and when to use it ("Use when the user wants to interact with Pendo data"), satisfying both halves with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Includes natural product-domain terms (Guides, Segments, Pages, Features, Feedbacks, Polls, Pendo) users would say, but is missing common synonyms and file-extension-style variations that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	The Pendo-specific entity names and "Pendo integration" framing carve a clear niche with minimal overlap risk against other skills' triggers.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/pendo/SKILL.md
Commit: f484c82

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.